Loading…
Loading…
Models / gemma-4-E4B
1 model (~8B) · ↓ 113.8K downloads a month · from $0.16/h on RTX 4060 Ti right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| it unsloth bnb 4bit (unsloth)unsloth/gemma-4-E4B-it-unsloth-bnb-4bit | vLLM | 11 GB | 15.2 GB | $0.16/h RTX 4060 Ti |
| it OBLITERATED (OBLITERATUS)OBLITERATUS/gemma-4-E4B-it-OBLITERATED | vLLM | 16 GB | 20.8 GB | $0.18/h 2x RTX 3060 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").